livekit-agents@1.2.9

livekit/agentslivekit-agents@1.2.9Sep 15, 2025by theomonnom

AI Summary

Focuses on OpenAI Realtime video support, new Ultravox plugin integration, and enhancements to AWS prompt caching and Groq plugin capabilities.

Key Highlights

  • OpenAI Realtime API now supports video input.
  • Added Ultravox Realtime API Plugin.
  • AWS Prompt Caching enabled for LLM requests.
  • Groq plugin support for timeout, max_retries, and service_tier.
  • Google TTS HD voices support added.

New Features

  • OpenAI Realtime video support.
  • Ultravox Realtime API Plugin.
  • AWS Prompt Caching.
  • Groq plugin enhancements.
  • Google TTS HD voices.

Full Release Notes

## Features:
- OpenAI Realtime API now supports video input

## What's Changed
* Add Ultravox Realtime API Plugin by @moadel321 in https://github.com/livekit/agents/pull/2992
* fix and clean ultravox realtime API plugin by @longcw in https://github.com/livekit/agents/pull/3339
* remove sentence tokenizer from transcription sync by @longcw in https://github.com/livekit/agents/pull/3334
* non-stream tts: raise no audio pushed error only if text is not empty by @longcw in https://github.com/livekit/agents/pull/3310
* fix speech resume when interrupted by interim transcript by @longcw in https://github.com/livekit/agents/pull/3299
* add preferred_alignment and fix alignment chars by @longcw in https://github.com/livekit/agents/pull/3341
* feat: Add support for Nebius AI Studio Models by @Arindam200 in https://github.com/livekit/agents/pull/3332
* feat(AWS): Enable prompt caching by @itskyf in https://github.com/livekit/agents/pull/3338
* plugins: groq: llm: add support for timeout and max_retries by @ssettle-groq in https://github.com/livekit/agents/pull/3350
* plugins: groq: llm: add support for service_tier by @ssettle-groq in https://github.com/livekit/agents/pull/3348
* Fix warning in model field access by @marctorsoc in https://github.com/livekit/agents/pull/3340
* chore(groq): accept additional options by @davidzhao in https://github.com/livekit/agents/pull/3370
* add ELEVEN_API_KEY to README for configuration by @Panmax in https://github.com/livekit/agents/pull/3371
* feat(azure-stt): add configurable punctuation option to Azure STT by @sarthakgoyal23 in https://github.com/livekit/agents/pull/3326
* fix transcription synchronizer cannot be closed if paused by @longcw in https://github.com/livekit/agents/pull/3378
* chore: add update_options for aws tts by @longcw in https://github.com/livekit/agents/pull/3384
* add text normalization param by @tinalenguyen in https://github.com/livekit/agents/pull/3390
* fix: improve FallbackAdapter streaming capability detection by @bnovik0v in https://github.com/livekit/agents/pull/3294
* fix user speaking span duration by @tinalenguyen in https://github.com/livekit/agents/pull/3404
* add realtime model tool calls to chat ctx by @longcw in https://github.com/livekit/agents/pull/3345
* make flush duration configurable in commit_user_turn by @longcw in https://github.com/livekit/agents/pull/3358
* use markdown and emoji filters for tts_node by default by @longcw in https://github.com/livekit/agents/pull/3305
* commit user turn before closing the AgentSession by @longcw in https://github.com/livekit/agents/pull/3377
* fix OAI realtime response created after generate_reply timeout by @longcw in https://github.com/livekit/agents/pull/3405
* add warning if use_tts_aligned_transcript is enabled but no transcript received from tts by @longcw in https://github.com/livekit/agents/pull/3409
* fix: Agent status was not updated when audio was paused. by @Panmax in https://github.com/livekit/agents/pull/3406
* don't ever send meta to openai by @guidodecaso in https://github.com/livekit/agents/pull/3402
* Revert "tune vad min_silence_duration and min_endpointing_delay (#2953)" by @longcw in https://github.com/livekit/agents/pull/3416
* Removed OpenAI-Beta header as per the docs by @MajorTal in https://github.com/livekit/agents/pull/3412
* add tool call and output to session.history by @longcw in https://github.com/livekit/agents/pull/3316
* fix(sarvam-tts): add bulbul:v3-beta support and make pitch/loudness optional by @21lakshh in https://github.com/livekit/agents/pull/3413
* chore: add keyterms support for AssemblyAI plugin by @dan-ince-aai in https://github.com/livekit/agents/pull/3387
* Revert "Removed OpenAI-Beta header as per the docs" by @longcw in https://github.com/livekit/agents/pull/3419
* feat(Google): Add markup for TTS HD voices by @itskyf in https://github.com/livekit/agents/pull/3281
* feat: update openai realtime API version to GA by @davidzhao in https://github.com/livekit/agents/pull/3420
* revert #3206, do not auto enable use_tts_aligned_transcript by @longcw in https://github.com/livekit/agents/pull/3423
* livekit-agents 1.2.9 by @theomonnom in https://github.com/livekit/agents/pull/3428

## New Contributors
* @moadel321 made their first contribution in https://github.com/livekit/agents/pull/2992
* @Arindam200 made their first contribution in https://github.com/livekit/agents/pull/3332
* @ssettle-groq made their first contribution in https://github.com/livekit/agents/pull/3350
* @marctorsoc made their first contribution in https://github.com/livekit/agents/pull/3340
* @sarthakgoyal23 made their first contribution in https://github.com/livekit/agents/pull/3326
* @21lakshh made their first contribution in https://github.com/livekit/agents/pull/3413

**Full Changelog**: https://github.com/livekit/agents/compare/livekit-agents@1.2.8...livekit-agents@1.2.9